Decode what a company's open roles reveal about its problems
Reads a company's open roles as evidence: what the hiring pattern says about scaling and rebuilding, which specific problems the postings confess to, what tools they name, what leadership vacancies mean for your deal, and the two best outreach hooks tied to it all. Job postings are the one public document marketing doesn't edit — this extracts everything they leak.
You are a workforce signals analyst who reads job boards the way detectives read crime scenes. A careers page is a company's most honest public document: every posting is a confession about what the org can't currently do, and marketing never gets to edit it. I'll paste a company's open roles — titles and descriptions, or their full careers page. You produce: 1. HIRING SHAPE — the pattern at a glance: how many roles, in which functions, at what seniority, and what that mix says (scaling sales? rebuilding engineering? first-ever hire in a function?). 2. CONFESSIONS — 3 to 5 specific inferences about problems or initiatives, each tied to posting evidence: a first DevOps hire confesses infrastructure pain; three SDR openings confess a pipeline push; a 'process improvement' bullet in an ops role confesses chaos. Grade each strong / plausible / speculative. 3. TOOL INTEL — every tool, platform, or methodology named in the postings, and what the stack glimpse implies. 4. SENIORITY TELLS — leadership roles open (who's missing at the top and what that vacancy means for deals) versus junior stacking (where they're adding capacity). 5. OUTREACH HOOKS — the 2 best angles connecting a hiring signal to what I sell, each with a one-sentence opener that references the posting naturally, not creepily. Rules: inferences must trace to specific postings — no reading tea leaves from a generic 'we're hiring!' banner. Note posting age if visible; a role open 6+ months is its own signal (they can't fill it, or it's evergreen). If the roles I paste are too few to pattern-read, say so and analyze the individual postings instead. Before you analyze, interview me. Ask me these questions ONE AT A TIME, waiting for my answer each time: 1. What does your product do, and which hiring patterns among your customers historically predict a good time to buy? 2. Paste the open roles — titles minimum, full descriptions ideally. 3. Who's your buyer at this company? 4. Roughly how big is the company? Ten open roles means different things at 50 versus 5,000 employees. Once you have my answers, run the read.
How to use it
- 1
Copy the prompt into Claude, ChatGPT, or any LLM.
- 2
Pull roles from the company's own careers page or LinkedIn jobs tab — paste full descriptions where possible, since the bullet points hold the confessions.
- 3
Answer question 1 with real patterns from your closed-won accounts if you know them.
- 4
Weight the CONFESSIONS by grade: sequence on strong, hold plausible for discovery.
- 5
Reference roles naturally in outreach ('saw you're bringing on a RevOps lead') — never quote a posting's bullet back at them.
Best practices
Full descriptions beat titles: the responsibilities section is where companies describe the mess the hire is meant to clean up.
A leadership vacancy in your buyer's function cuts both ways — deals stall without an owner, but the incoming leader is your best future champion. Time outreach for their arrival.
Cross-check posting age where shown: a director role open seven months signals either a search problem or a budget mirage.
To monitor at scale, wire a job-postings enrichment into Clay and re-run this read monthly on tier-one accounts — hiring pages turn over fast.
Example: what this looks like in practice
An AE at a marketing-automation platform pastes 14 open roles from a 300-person B2B software company. The read: five sales roles including a first-ever 'Head of SDR' (strong confession: building outbound from scratch), a 'Marketing Ops Manager' posting requiring 'experience migrating marketing automation platforms' (strong: they're switching tools), and HubSpot named in three postings. The model flags the migration bullet as the lead hook. Her opener references the ops role and asks what's driving the migration. The reply names the incumbent vendor and the renewal date — intel that usually takes three discovery calls to surface.
Best fit
This prompt is one gear in a bigger machine. We orchestrate 20+ tools into outbound systems our clients own — and guarantee the results.
Apply for a Pilot Spot → →Frequently asked questions
More than any other free source: postings reveal growth areas, admitted problems (the responsibilities section describes the mess the hire will inherit), tech stack (required-experience bullets name tools), leadership gaps, and budget reality. A careers page is effectively a confession log — this prompt reads it systematically instead of skimming titles.
More account & prospect research prompts
Build a 10-minute company deep-dive brief before you touch an account
Produces a one-page, source-backed account brief with a fixed six-section structure: snapshot, revenue logic, recent momentum, evidence-based pressures, two outreach angles, and landmines to avoid. It compresses the hour of tab-hopping most reps do before a tier-one account into ten minutes, and forces every claim to carry a source.
Scan an account for trigger events: news, funding, leadership moves, layoffs
Runs a structured six-month trigger-event sweep on one account — funding, leadership changes, layoffs, launches, expansion, legal news — and returns a dated, sourced signal log, the top three events ranked by outreach value, a ready-to-adapt angle for the best one, and an honest timing call including 'no trigger exists.' It turns 'why now' from a guess into evidence.
Audit a prospect list for quality before a single email goes out
Audits a prospect list before launch: completeness and duplicates, out-of-ICP rows, stale-data risks, deliverability hazards like role-based emails and sequence collisions, and an honest A-F grade with a prioritized fix list. It catches the problems that get misdiagnosed as 'copy issues' three weeks and one burned domain later.